Zijian Zhou, Preetesh Jain, Yang Lu, Homer Macapinlac, Michael L Wang, Jong Bum Son, Mark D Pagel, Guofan Xu, Jingfei Ma
{"title":"基于深度学习卷积神经网络的18F-FDG PET/CT套细胞淋巴瘤计算机辅助检测","authors":"Zijian Zhou, Preetesh Jain, Yang Lu, Homer Macapinlac, Michael L Wang, Jong Bum Son, Mark D Pagel, Guofan Xu, Jingfei Ma","doi":"","DOIUrl":null,"url":null,"abstract":"<p><p><sup>18</sup>F-FDG PET/CT can provide quantitative characterization with prognostic value for mantle cell lymphoma (MCL). However, detection of MCL is performed manually, which is labor intensive and not a part of the routine clinical practice. This study investigates a deep learning convolutional neural network (DLCNN) for computer-aided detection of MCL on <sup>18</sup>F-FDG PET/CT. We retrospectively analyzed 142 baseline <sup>18</sup>F-FDG PET/CT scans of biopsy-confirmed MCL acquired between May 2007 and October 2018. Of the 142 scans, 110 were from our institution and 32 were from outside institutions. An Xception-based U-Net was constructed to classify each pixel of the PET/CT images as MCL or not. The network was first trained and tested on the within-institution scans by applying five-fold cross-validation. Sensitivity and false positives (FPs) per patient were calculated for network evaluation. The network was then tested on the outside-institution scans, which were excluded from network training. For the 110 within-institution patients (85 male; median age, 58 [range: 39-84] years), the network achieved an overall median sensitivity of 88% (interquartile range [IQR]: 25%) with 15 (IQR: 12) FPs/patient. Sensitivity was dependent on lesion size and SUV<sub>max</sub> but not on lesion location. For the 32 outside-institution patients (24 male; median age, 59 [range: 40-67] years), the network achieved a median sensitivity of 84% (IQR: 24%) with 14 (IQR: 10) FPs/patient. No significant performance difference was found between the within and outside institution scans. Therefore, DLCNN can potentially help with MCL detection on <sup>18</sup>F-FDG PET/CT with high sensitivity and limited FPs.</p>","PeriodicalId":7572,"journal":{"name":"American journal of nuclear medicine and molecular imaging","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2021-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8414404/pdf/ajnmmi0011-0260.pdf","citationCount":"0","resultStr":"{\"title\":\"Computer-aided detection of mantle cell lymphoma on <sup>18</sup>F-FDG PET/CT using a deep learning convolutional neural network.\",\"authors\":\"Zijian Zhou, Preetesh Jain, Yang Lu, Homer Macapinlac, Michael L Wang, Jong Bum Son, Mark D Pagel, Guofan Xu, Jingfei Ma\",\"doi\":\"\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><sup>18</sup>F-FDG PET/CT can provide quantitative characterization with prognostic value for mantle cell lymphoma (MCL). However, detection of MCL is performed manually, which is labor intensive and not a part of the routine clinical practice. This study investigates a deep learning convolutional neural network (DLCNN) for computer-aided detection of MCL on <sup>18</sup>F-FDG PET/CT. We retrospectively analyzed 142 baseline <sup>18</sup>F-FDG PET/CT scans of biopsy-confirmed MCL acquired between May 2007 and October 2018. Of the 142 scans, 110 were from our institution and 32 were from outside institutions. An Xception-based U-Net was constructed to classify each pixel of the PET/CT images as MCL or not. The network was first trained and tested on the within-institution scans by applying five-fold cross-validation. Sensitivity and false positives (FPs) per patient were calculated for network evaluation. The network was then tested on the outside-institution scans, which were excluded from network training. For the 110 within-institution patients (85 male; median age, 58 [range: 39-84] years), the network achieved an overall median sensitivity of 88% (interquartile range [IQR]: 25%) with 15 (IQR: 12) FPs/patient. Sensitivity was dependent on lesion size and SUV<sub>max</sub> but not on lesion location. For the 32 outside-institution patients (24 male; median age, 59 [range: 40-67] years), the network achieved a median sensitivity of 84% (IQR: 24%) with 14 (IQR: 10) FPs/patient. No significant performance difference was found between the within and outside institution scans. Therefore, DLCNN can potentially help with MCL detection on <sup>18</sup>F-FDG PET/CT with high sensitivity and limited FPs.</p>\",\"PeriodicalId\":7572,\"journal\":{\"name\":\"American journal of nuclear medicine and molecular imaging\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2021-08-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8414404/pdf/ajnmmi0011-0260.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"American journal of nuclear medicine and molecular imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2021/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of nuclear medicine and molecular imaging","FirstCategoryId":"1085","ListUrlMain":"","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Computer-aided detection of mantle cell lymphoma on 18F-FDG PET/CT using a deep learning convolutional neural network.
18F-FDG PET/CT can provide quantitative characterization with prognostic value for mantle cell lymphoma (MCL). However, detection of MCL is performed manually, which is labor intensive and not a part of the routine clinical practice. This study investigates a deep learning convolutional neural network (DLCNN) for computer-aided detection of MCL on 18F-FDG PET/CT. We retrospectively analyzed 142 baseline 18F-FDG PET/CT scans of biopsy-confirmed MCL acquired between May 2007 and October 2018. Of the 142 scans, 110 were from our institution and 32 were from outside institutions. An Xception-based U-Net was constructed to classify each pixel of the PET/CT images as MCL or not. The network was first trained and tested on the within-institution scans by applying five-fold cross-validation. Sensitivity and false positives (FPs) per patient were calculated for network evaluation. The network was then tested on the outside-institution scans, which were excluded from network training. For the 110 within-institution patients (85 male; median age, 58 [range: 39-84] years), the network achieved an overall median sensitivity of 88% (interquartile range [IQR]: 25%) with 15 (IQR: 12) FPs/patient. Sensitivity was dependent on lesion size and SUVmax but not on lesion location. For the 32 outside-institution patients (24 male; median age, 59 [range: 40-67] years), the network achieved a median sensitivity of 84% (IQR: 24%) with 14 (IQR: 10) FPs/patient. No significant performance difference was found between the within and outside institution scans. Therefore, DLCNN can potentially help with MCL detection on 18F-FDG PET/CT with high sensitivity and limited FPs.
期刊介绍:
The scope of AJNMMI encompasses all areas of molecular imaging, including but not limited to: positron emission tomography (PET), single-photon emission computed tomography (SPECT), molecular magnetic resonance imaging, magnetic resonance spectroscopy, optical bioluminescence, optical fluorescence, targeted ultrasound, photoacoustic imaging, etc. AJNMMI welcomes original and review articles on both clinical investigation and preclinical research. Occasionally, special topic issues, short communications, editorials, and invited perspectives will also be published. Manuscripts, including figures and tables, must be original and not under consideration by another journal.